-
Gait & Posture Jun 2024Gait abnormality detection is a challenging task in clinical practice. The majority of the current frameworks for gait abnormality detection involve the individual...
BACKGROUND
Gait abnormality detection is a challenging task in clinical practice. The majority of the current frameworks for gait abnormality detection involve the individual processes of segmentation, feature estimation, feature learning, and similarity assessment. Since each component of these modules is fixed and they are mutually independent, their performance under difficult circumstances is not ideal. We combine those processes into a single framework, a gait abnormality detection system with an end-to-end network.
METHODS
It is made up of convolutional neural networks and Deep-Q-learning methods: one for coordinate estimation and the other for classification. In a single joint learning technique that may be trained together, the two networks are modeled. This method is significantly more efficient for use in real life since it drastically simplifies the conventional step-by-step approach.
RESULTS
The proposed model is experimented on MATLAB R2020a. While considering into consideration the stability factor, our proposed model attained an average case accuracy of 95.3%, a sensitivity of 96.4%, and a specificity of 94.1%.
SIGNIFICANCE
Our paradigm for quantifying gait analysis using commodity equipment will improve access to quantitative gait analysis in medical facilities and rehabilitation centers while also allowing academics to conduct large-scale investigations for gait-related disorders. Numerous experimental findings demonstrate the effectiveness of the proposed strategy and its ability to provide cutting-edge outcomes.
PubMed: 38954927
DOI: 10.1016/j.gaitpost.2024.06.010 -
Waste Management (New York, N.Y.) Jul 2024Rapid expansion in urban areas has engendered a superfluity of municipal solid waste (MSW) stemming from contemporary civilization, encompassing commercial sectors and...
Rapid expansion in urban areas has engendered a superfluity of municipal solid waste (MSW) stemming from contemporary civilization, encompassing commercial sectors and human undertakings. Kerbside waste, a type of MSW, has the potential for recycling and reuse at the end of its first life cycle, but is often limited to a linear cycle. This study aimed to assess the life cycle costs of different separation and recycling methods for handling kerbside waste. A new life cycle cost model, drawing from the circular economy's value retention process (VRP) model, has been created and applied to assess the continuous recycling of kerbside glass. The study investigates two key separation techniques, kerbside recycling mixed bin recycling (KRMB) kerbside glass recycling separate bin (KGRSB) and analyses their impact on the life cycle cost of the recycling process. Additionally, the research explores two approaches of recycling and downcycling: closed-loop recycling, which pertains to the recycling of glass containers, and open-looped recycling, which involves the use of recycled glass in asphalt. The results showed when use annually collected waste as the functional unit, the KRMB model incurred lower costs compared to the KGRSB model due to its lower production output. However, when evaluated over a 1-ton production of glass container and asphalt, the KGRSB method demonstrated superior cost performance with a 40-50% reduction compared to the KRMB method. The open-loop recycling method (asphalt) incurred a higher cost compared to the closed-loop recycling method due to its larger production volume over a 21-year period.
PubMed: 38954922
DOI: 10.1016/j.wasman.2024.06.023 -
Computer Methods and Programs in... Jun 2024In ultrasound guided high-intensity focused ultrasound (HIFU) surgery, it is necessary to transmit sound waves at different frequencies simultaneously using two...
BACKGROUND AND OBJECTIVES
In ultrasound guided high-intensity focused ultrasound (HIFU) surgery, it is necessary to transmit sound waves at different frequencies simultaneously using two transducers: one for the HIFU therapy and another for the ultrasound imaging guidance. In this specific setting, real-time monitoring of non-invasive surgery is challenging due to severe contamination of the ultrasound guiding images by strong acoustic interference from the HIFU sonication.
METHODS
This paper proposed the use of a deep learning (DL) solution, specifically a diffusion implicit model, to suppress the HIFU interference. We considered the images contaminated with HIFU interference as low-resolution images, and those free from interference as high-resolution. While suppressing HIFU interference using the diffusion implicit (HIFU-Diff) model, the task was transformed into generating a high-resolution image through a series of forward diffusion steps and reverse sampling. A series of ex-vivo and in-vivo experiments, conducted under various parameters, were designed to validate the performance of the proposed network.
RESULTS
Quantitative evaluation and statistical analysis demonstrated that the HIFU-Diff network achieved superior performance in reconstructing interference-free images under a variety of ex-vivo and in-vivo conditions, compared to the most commonly used notch filtering and the recent 1D FUS-Net deep learning network. The HIFU-Diff maintains high performance with 'unseen' datasets from separate experiments, and its superiority is more pronounced under strong HIFU interferences and in complex in-vivo situations. Furthermore, the reconstructed interference-free images can also be used for quantitative attenuation imaging, indicating that the network preserves acoustic characteristics of the ultrasound images.
CONCLUSIONS
With the proposed technique, HIFU therapy and the ultrasound imaging can be conducted simultaneously, allowing for real-time monitoring of the treatment process. This capability could significantly enhance the safety and efficacy of the non-invasive treatment across various clinical applications. To the best of our knowledge, this is the first diffusion-based model developed for HIFU interference suppression.
PubMed: 38954917
DOI: 10.1016/j.cmpb.2024.108304 -
European Journal of Radiology Jun 2024When treating Lung Cancer, it is necessary to identify early treatment failure to enable timely therapeutic adjustments. The Aim of this study was to investigate whether...
Diffusion weighted MRI and apparent diffusion coefficient as a prognostic biomarker in evaluating chemotherapy-antiangiogenic treated stage IV non-small cell lung cancer: A prospective, single-arm, open-label, clinical trial (BevMar).
PURPOSE
When treating Lung Cancer, it is necessary to identify early treatment failure to enable timely therapeutic adjustments. The Aim of this study was to investigate whether changes in tumor diffusion during treatment with chemotherapy and bevacizumab could serve as a predictor of treatment failure.
MATERIAL AND METHODS
A prospective single-arm, open-label, clinical trial was conducted between September 2014 and December 2020, enrolling patients with stage IV non-small cell lung cancer (NSCLC). The patients were treated with chemotherapy-antiangiogenic combination. Diffusion weighted magnetic resonance imaging (DW-MRI) was performed at baseline, two, four, and sixteen weeks after initiating treatment. The differences in apparent diffusion coefficient (ADC) values between pre- and post-treatment MRIs were recorded as Delta values (ΔADC). We assessed whether ΔADC could serve as a prognostic biomarker for overall survival (OS), with a five year follow up.
RESULTS
18 patients were included in the final analysis. Patients with a ΔADC value ≥ -3 demonstrated a significantly longer OS with an HR of 0.12 (95 % CI; 0.03- 0.61; p = 0.003) The median OS in patients with a ΔADC value ≥ -3 was 18 months, (95 % C.I; 7-46) compared to 7 months (95 % C.I; 5-9) in those with a ΔADC value < -3.
CONCLUSION
Our findings suggest that early changes in tumor ADC values, may be indicative of a longer OS. Therefore, DW-MRI could serve as an early biomarker for assessing treatment response in patients receiving chemotherapy combined with antiangiogenic therapy.
PubMed: 38954912
DOI: 10.1016/j.ejrad.2024.111557 -
Biosensors & Bioelectronics Jun 2024Neurotransmitters (NTs) are molecules produced by neurons that act as the body's chemical messengers. Their abnormal levels in the human system have been associated with...
Neurotransmitters (NTs) are molecules produced by neurons that act as the body's chemical messengers. Their abnormal levels in the human system have been associated with many disorders and neurodegenerative diseases, which makes the monitoring of NTs fundamentally important. Specifically for clinical analysis and understanding of brain behavior, simultaneous detection of NTs at low levels quickly and reliably is imperative for disease prevention and early diagnosis. However, the methods currently employed are usually invasive or inappropriate for multiple NTs detection. Herein, we developed a MXene-based impedimetric electronic tongue (e-tongue) for sensitive NT monitoring, using NbC, NbC, MoC, and MoTiC MXenes as sensing units of the e-tongue, and Principal Component Analysis (PCA) as the data treatment method. The high specific surface area, distinct electrical properties, and chemical stability of the MXenes gave rise to high sensitivity and good reproducibility of the sensor array toward NT detection. Specifically, the e-tongue detected and differentiated multiple NTs (acetylcholine, dopamine, glycine, glutamate, histamine, and tyrosine) at concentrations as low as 1 nmol L and quantified NTs present in a mixture. Besides, analyses performed with interferents and actual samples confirmed the system's potential to be used in clinical diagnostics. The results demonstrate that the MXene-based e-tongue is a suitable, rapid, and simple method for NT monitoring with high accuracy and sensitivity.
PubMed: 38954905
DOI: 10.1016/j.bios.2024.116526 -
European Journal of Cancer (Oxford,... Jun 2024The prognosis of patients with advanced biliary tract cancer (BTC) is still poor, and new strategies improving patients' outcome are needed. In our trial we investigated...
INTRODUCTION
The prognosis of patients with advanced biliary tract cancer (BTC) is still poor, and new strategies improving patients' outcome are needed. In our trial we investigated safety and activity of nab-paclitaxel in combination with gemcitabine and oxaliplatin as first-line systemic treatment for patients with advanced BTC.
METHODS
In this investigator-initiated, multicenter, dose-escalation, single-arm phase I/II trial, patients were accrued into cohorts of 3 patients and dose escalation was performed following the standard 3 + 3 rule. Primary endpoint was the proportion of patients free from progression at 6 months. Secondary endpoints included safety and tolerability of the combination; progression-free survival (PFS); overall survival (OS); objective response rate (ORR); duration of response.
RESULTS
Between July 2017 and December 2020, 67 patients were treated. Among the 10 patients in the phase I, no dose-limiting toxicity was observed, and dose level 2 was defined as recommended phase II dose for the phase II part. At data cutoff, the 6-month PFS rate was 49.1 % (95 % CI 40.8-57.5 %) with 28 patients out of 57 free from progression or death at 6 months. Median PFS was 6.3 months (95 % CI 3.6-10.1) and median OS was 12.4 months (95 % CI 8-23). ORR was 20.89 %. Most common grade 3 and grade 1-2 drug-related adverse events were neutropenia and peripheral neuropathy, respectively.
CONCLUSION
Triple chemotherapy demonstrated a favorable safety profile. However, the study did not meet its primary endpoint. Future studies will clarify the benefit of chemotherapy combinations in different settings. This trial is registered with ClinicalTrials.gov, NCT03943043.
PubMed: 38954899
DOI: 10.1016/j.ejca.2024.114196 -
Neural Networks : the Official Journal... Jun 2024Graph neural networks (GNNs) have demonstrated exceptional performance in processing various types of graph data, such as citation networks and social networks, etc....
Graph neural networks (GNNs) have demonstrated exceptional performance in processing various types of graph data, such as citation networks and social networks, etc. Although many of these GNNs prove their superiority in handling homophilic graphs, they often overlook the other kind of widespread heterophilic graphs, in which adjacent nodes tend to have different classes or dissimilar features. Recent methods attempt to address heterophilic graphs from the graph spatial domain, which try to aggregate more similar nodes or prevent dissimilar nodes with negative weights. However, they may neglect valuable heterophilic information or extract heterophilic information ineffectively, which could cause poor performance of downstream tasks on heterophilic graphs, including node classification and graph classification, etc. Hence, a novel framework named GARN is proposed to effectively extract both homophilic and heterophilic information. First, we analyze the shortcomings of most GNNs in tackling heterophilic graphs from the perspective of graph spectral and spatial theory. Then, motivated by these analyses, a Graph Aggregating-Repelling Convolution (GARC) mechanism is designed with the objective of fusing both low-pass and high-pass graph filters. Technically, it learns positive attention weights as a low-pass filter to aggregate similar adjacent nodes, and learns negative attention weights as a high-pass filter to repel dissimilar adjacent nodes. A learnable integration weight is used to adaptively fuse these two filters and balance the proportion of the learned positive and negative weights, which could control our GARC to evolve into different types of graph filters and prevent it from over-relying on high intra-class similarity. Finally, a framework named GARN is established by simply stacking several layers of GARC to evaluate its graph representation learning ability on both the node classification and image-converted graph classification tasks. Extensive experiments conducted on multiple homophilic and heterophilic graphs and complex real-world image-converted graphs indicate the effectiveness of our proposed framework and mechanism over several representative GNN baselines.
PubMed: 38954894
DOI: 10.1016/j.neunet.2024.106484 -
Neural Networks : the Official Journal... Jun 2024In reinforcement learning, accurate estimation of the Q-value is crucial for acquiring an optimal policy. However, current successful Actor-Critic methods still suffer...
In reinforcement learning, accurate estimation of the Q-value is crucial for acquiring an optimal policy. However, current successful Actor-Critic methods still suffer from underestimation bias. Additionally, there exists a significant estimation bias, regardless of the method used in the critic initialization phase. To address these challenges and reduce estimation errors, we propose CEILING, a simple and compatible framework that can be applied to any model-free Actor-Critic methods. The core idea of CEILING is to evaluate the superiority of different estimation methods by incorporating the true Q-value, calculated using Monte Carlo, during the training process. CEILING consists of two implementations: the Direct Picking Operation and the Exponential Softmax Weighting Operation. The first implementation selects the optimal method at each fixed step and applies it in subsequent interactions until the next selection. The other implementation utilizes a nonlinear weighting function that dynamically assigns larger weights to more accurate methods. Theoretically, we demonstrate that our methods provide a more accurate and stable Q-value estimation. Additionally, we analyze the upper bound of the estimation bias. Based on two implementations, we propose specific algorithms and their variants, and our methods achieve superior performance on several benchmark tasks.
PubMed: 38954893
DOI: 10.1016/j.neunet.2024.106483 -
Psychiatry Research Jun 2024Recovery from a COVID-19 infection can lead to post-COVID-19 condition (PCC), which causes a multitude of debilitating symptoms that negatively affect an individual's...
OBJECTIVE
Recovery from a COVID-19 infection can lead to post-COVID-19 condition (PCC), which causes a multitude of debilitating symptoms that negatively affect an individual's health-related quality of life, including depressive and anxiety symptoms. We aim to examine the mediatory effects of anxiety on depressive symptoms in persons with PCC receiving vortioxetine.
METHODS
We performed a post-hoc analysis of a randomized, double-blinded, placebo-controlled clinical trial investigating vortioxetine treatment on cognitive functioning in persons with PCC. Anxiety and depressive symptoms were measured by the 7-Item Generalized Anxiety Disorder (GAD-7) Scale and the 16-Item Quick Inventory of Depressive Symptomatology (QIDS-SR-16), respectively.
RESULTS
Based on data of 147 participants, GAD-7 scores were significantly positively associated with QIDS-SR-16 scores (β=0.038, 95 % CI [0.029,0.047], p < 0.001). After adjusting for covariates, a significant group (χ=176.786, p < 0.001), time (χ=8.914, p = 0.003), and treatment x time x GAD-7 score interaction (χ=236.483, p < 0.001) effect was observed. Vortioxetine-treated participants had a significant difference in overall change in depressive symptoms (mean difference=-3.15, SEM=0.642, 95 % CI [-4.40,-1.89], p < 0.001).
CONCLUSION
Anxiety symptoms were significantly associated with depressive symptoms in persons with PCC. Antidepressant efficacy on ameliorating depressive symptoms is dependent on improving anxiety symptoms, underscoring significant implications in improving treatment efficacy and patient quality of life.
PubMed: 38954891
DOI: 10.1016/j.psychres.2024.116068 -
Clinical Biomechanics (Bristol, Avon) Jun 2024Severity of dyskinesia in children with cerebral palsy is often assessed using observation-based clinical tools. Instrumented methods to objectively measure dyskinesia...
BACKGROUND
Severity of dyskinesia in children with cerebral palsy is often assessed using observation-based clinical tools. Instrumented methods to objectively measure dyskinesia have been proposed to improve assessment accuracy and reliability. Here, we investigated the technique and movement features that were most suitable to objectively measure the severity of dystonia in children with cerebral palsy.
METHODS
A prospective observational study was conducted with 12 participants with cerebral palsy with a predominant motor type of dyskinesia, spasticity, or mixed dyskinesia/spasticity who had upper limb involvement (mean age: 12.6 years, range: 6.7-18.2 years). Kinematic and electromyography data were collected bilaterally during three upper limb tasks. Spearman rank correlations of kinematic or electromyography features were calculated against dystonia severity, quantified by the Dyskinesia Impairment Scale.
FINDINGS
Kinematic features were more influential compared to electromyography features at grading the severity of dystonia in children with cerebral palsy. Kinematic measures quantifying jerkiness of volitional movement during an upper limb task with a reaching component performed best (|r| = 0.78-0.9, p < 0.001).
INTERPRETATION
This study provides guidance on the types of data, features of movement, and activity protocols that instrumented methods should focus on when objectively measuring the severity of dystonia in children with cerebral palsy.
PubMed: 38954886
DOI: 10.1016/j.clinbiomech.2024.106295